Benchmark
MAST (Medical AI Superintelligence Test)
Scores are percentages. Higher is better.
Benchmark sourceScores from Clinical Benchmarks data docs.
- Models measured
- 8
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 0.80
Score distribution
- 58%
- Mean
- 58.9%
- Median
- 2%
- Std dev
- 56.6%
- 10th percentile
- 60.1%
- 90th percentile
- 53.7%
- Min
This benchmark has a weight of 0.80 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Solclinical-result-106· Clinical Benchmarks data docs | 60.2% |
| 2 | Kimi K3clinical-result-107· Clinical Benchmarks data docs | 60.1% |
| 3 | Gemini 3.6 Flashclinical-result-108· Clinical Benchmarks data docs | 59.3% |
| 4 | Gemini 3.1 Pro Previewclinical-result-109· Clinical Benchmarks data docs | 58.9% |
| 5 | Qwen3.5 397B A17Bclinical-result-110· Clinical Benchmarks data docs | 57.9% |
| 6 | Claude Opus 5clinical-result-111· Clinical Benchmarks data docs | 57.1% |
| 7 | Claude Sonnet 5clinical-result-112· Clinical Benchmarks data docs | 56.6% |
| 8 | Grok 4.3clinical-result-113· Clinical Benchmarks data docs | 53.7% |
Data credits: Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)